© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 31-TRANSCODER-HP
    7. 19968
    Prev
    Next
    INDEX
    Explanations

    New

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    èķĥ
    -0.29
     anon
    -0.26
     CB
    -0.26
    èĮģ
    -0.26
    PFN
    -0.25
    lore
    -0.25
    ãĥĹãĥŃ
    -0.25
    涣
    -0.24
     Painter
    -0.24
    峦
    -0.24
    POSITIVE LOGITS
     midterm
    0.27
    itti
    0.26
    è£Ĩ
    0.26
    æĸŃ
    0.26
    åĺī
    0.26
    chart
    0.26
    ari
    0.25
    裤
    0.25
     Attend
    0.25
    arium
    0.25
    Activations Density 0.058%

    No Known Activations